Module 2: Introduction to IE and ANNIE - Gate

147 Pages·2011·1.13 MB·English

University of Sheffield NLP
Module 2: Introduction to IE and
ANNIE
© The University of Sheffield, 1995-2010
This work is licenced under the Creative Commons Attribution-NonCommercial-ShareAlike Licence.
University of Sheffield NLP
About this tutorial
This tutorial comprises the following topics:
Introduction to IE

ANNIE

Multilingual tools in GATE

Evaluation and Corpus Quality Assurance

In Module 3, you’ll learn how to use JAPE, the
pattern matching language that many PRs use
University of Sheffield NLP
Tutorial outline
09:45– What is information extraction?
11:15 Examples of IE systems
ANNIE
Basic lexico-syntactic PRs
11:15– BREAK
11:45
11:45– Gazetteers, transducers, coreference
13:15 Modifying ANNIE
Multilingual IE
13:15– LUNCH
14.15
Evaluation
14:15–
Annotation Diff
15:45
Corpus Quality Assurance
15:45– COFFEE
16:15
16:15– INVITED TALK – GATE for Lifesciences
17:15
University of Sheffield NLP
What is information
extraction?
University of Sheffield NLP
IE is not IR
• IR pulls documents
from large text
collections (usually the
Web) in response to
specific keywords or
queries. You analyse
the documents.
• IE pulls facts and
structured information
from the content of large
text collections. You
analyse the facts.
University of Sheffield NLP
IE for Document Access
With traditional query engines, getting the facts can be

hard and slow
Where has the Queen visited in the last year?

Which airports are currently closed due to the

volcanic ash?
Which search terms would you use to get thess?

How can you specify you want to see someone’s home

page?
IE returns information in a structured way

IR returns documents containing the relevant information

somewhere
University of Sheffield NLP
IE as an alternative to IR
IE returns knowledge at a much deeper level

than traditional IR
It allows you to specify your query in a more

structured way
Constructing a database through IE and

linking it back to the documents can provide a
valuable alternative search tool
Even if results are not always accurate, they

can be valuable if linked back to the original
text
University of Sheffield NLP
What is IE used for?
IE is an enabling technology for many

other applications:
Text Mining

Semantic Annotation

Question Answering

Opinion Mining

Decision Support

Rich information retrieval and exploration

and so on..

University of Sheffield NLP
Two main types of IE systems
Knowledge Engineering Learning Systems
 rule based use statistics or other
machine learning
developed by experienced

language engineers developers do not need LE
expertise
make use of human

intuition require large amounts of
annotated training data
require only small amount

of training data some changes may require
re-annotation of the
development can be very

entire training corpus
time consuming
some changes may be

hard to accommodate
University of Sheffield NLP
Named Entity Recognition:
the cornerstone of IE
Traditionally, NE is the identification of proper names in texts,
and their classification into a set of predefined categories
of interest
Person

Organisation (companies, government organisations,

committees, etc)
Location (cities, countries, rivers, etc)

Date and time expressions

Various other types are frequently added, as appropriate to the
application, e.g. newspapers, ships, monetary amounts,
percentages etc.